twenty20batting2007 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2007twenty20battingrating.csv")
twenty20batting2008 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2008twenty20battingrating.csv")
twenty20batting2009 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2009twenty20battingrating.csv")
twenty20batting2010 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2010twenty20battingrating.csv")
twenty20batting2011 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2011twenty20battingrating.csv")
twenty20batting2012 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2012twenty20battingrating.csv")
twenty20batting2013 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2013twenty20battingrating.csv")
twenty20batting2014 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2014twenty20battingrating.csv")
twenty20batting2015 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2015twenty20battingrating.csv")
twenty20batting2016 <- read.csv("D:\\Vishal\\III year\\Data Analytics\\Assignment II\\Player Ratings\\2016twenty20battingrating.csv")
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
dataTwenty20Batting <- bind_rows(twenty20batting2007, twenty20batting2008, twenty20batting2009, twenty20batting2010,
twenty20batting2011, twenty20batting2012, twenty20batting2013, twenty20batting2014,
twenty20batting2015, twenty20batting2016)
## Warning in bind_rows_(x, .id): Unequal factor levels: coercing to character
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
## Warning in bind_rows_(x, .id): binding character and factor vector,
## coercing into character vector
summary(dataTwenty20Batting)
## Name Rating
## Length:1000 Min. : 10.0
## Class :character 1st Qu.:201.0
## Mode :character Median :316.5
## Mean :349.1
## 3rd Qu.:484.0
## Max. :897.0
library(VIM)
## Loading required package: colorspace
## Loading required package: grid
## Loading required package: data.table
##
## Attaching package: 'data.table'
## The following objects are masked from 'package:dplyr':
##
## between, first, last
## VIM is ready to use.
## Since version 4.0.0 the GUI is in its own package VIMGUI.
##
## Please use the package to use the new (and old) GUI.
## Suggestions and bug-reports can be submitted at: https://github.com/alexkowa/VIM/issues
##
## Attaching package: 'VIM'
## The following object is masked from 'package:datasets':
##
## sleep
aggr(dataTwenty20Batting)
dataTwenty20Batting <- dataTwenty20Batting %>%
group_by(Name) %>%
summarise(avg = mean(Rating))
set.seed(20)
batcluster <- kmeans(dataTwenty20Batting[, 2], 5)
batcluster$cluster <- as.factor(batcluster$cluster)
library(ggplot2)
library(DT)
ggplot(dataTwenty20Batting, aes(dataTwenty20Batting$Name, avg, color = batcluster$cluster)) +
geom_point(size = 2) +
theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
ggtitle("Twenty20 Batting Ratings(2007-2016)")
dat <- arrange(dataTwenty20Batting, desc(avg)) %>%
mutate(rank = 1:nrow(dataTwenty20Batting))
dataTwenty20Batting <- merge(dataTwenty20Batting, dat, by = "Name")
dataTwenty20Batting
## Name avg.x avg.y rank
## 1 Abdul Razzaq 59.0000 59.0000 254
## 2 Alok Kapali 72.0000 72.0000 250
## 3 Farhad Reza 78.0000 78.0000 249
## 4 Kamran Akmal 117.0000 117.0000 235
## 5 Mashrafe Mortaza 118.0000 118.0000 234
## 6 Naved ul Hasan 83.0000 83.0000 247
## 7 Salman Butt 114.0000 114.0000 236
## 8 A A Obanda 158.8000 158.8000 216
## 9 A B de Villiers 421.7000 421.7000 56
## 10 A Bagai 287.7500 287.7500 125
## 11 A C Botha 151.0000 151.0000 219
## 12 A C Gilchrist 219.0000 219.0000 178
## 13 A C L Richards 13.0000 13.0000 280
## 14 A D Hales 738.4000 738.4000 1
## 15 A D Mascarenhas 111.5000 111.5000 238
## 16 A D Mathews 388.5000 388.5000 70
## 17 A D Poynter 242.0000 242.0000 160
## 18 A D S Fletcher 262.7500 262.7500 146
## 19 A Flintoff 32.0000 32.0000 265
## 20 A J Finch 594.8333 594.8333 14
## 21 A J Redmond 253.0000 253.0000 153
## 22 A J Strauss 174.0000 174.0000 203
## 23 A M Rahane 289.7500 289.7500 124
## 24 A M Samad 159.0000 159.0000 214
## 25 A N Cook 44.0000 44.0000 259
## 26 A N Kervezee 282.0000 282.0000 131
## 27 A Nel 16.0000 16.0000 274
## 28 A P Devcich 228.0000 228.0000 171
## 29 A R Cusack 173.6667 173.6667 204
## 30 A R White 171.0000 171.0000 205
## 31 A Symonds 533.5000 533.5000 22
## 32 Abdul Razzaq 254.6000 254.6000 152
## 33 Abdur Rehman 13.0000 13.0000 281
## 34 Adnan Ilyas 343.0000 343.0000 89
## 35 Aftab Ahmed 277.3333 277.3333 137
## 36 Ahmed Shehzad 452.0000 452.0000 42
## 37 Anamul Haque 430.0000 430.0000 52
## 38 Asghar Stanikzai 291.0000 291.0000 122
## 39 B B McCullum 662.0000 662.0000 5
## 40 B J Haddin 250.1667 250.1667 156
## 41 B J Hodge 165.0000 165.0000 210
## 42 B Lee 159.3333 159.3333 213
## 43 B M A J Mendis 281.0000 281.0000 134
## 44 B N Cooper 271.0000 271.0000 140
## 45 B R M Taylor 364.4286 364.4286 84
## 46 Babar Hayat 453.0000 453.0000 41
## 47 C A Ingram 311.0000 311.0000 110
## 48 C D Barnwell 226.0000 226.0000 173
## 49 C D McMillan 72.0000 72.0000 251
## 50 C H Gayle 657.8000 657.8000 7
## 51 C J Anderson 261.0000 261.0000 149
## 52 C J Chibhabha 304.2222 304.2222 113
## 53 C K Coventry 179.0000 179.0000 199
## 54 C K Kapugedera 223.5000 223.5000 176
## 55 C K Langeveldt 19.0000 19.0000 269
## 56 C Kieswetter 473.6667 473.6667 32
## 57 C L White 434.3750 434.3750 49
## 58 C Munro 324.0000 324.0000 95
## 59 C O Obuya 209.2000 209.2000 182
## 60 C R D Fernando 79.5000 79.5000 248
## 61 C R Ervine 199.6667 199.6667 188
## 62 C S MacLeod 265.5000 265.5000 145
## 63 D A Miller 365.8333 365.8333 83
## 64 D A Warner 660.2500 660.2500 6
## 65 D F Watts 128.0000 128.0000 229
## 66 D J G Sammy 204.0000 204.0000 184
## 67 D J Hussey 591.2500 591.2500 15
## 68 D J J Bravo 380.2000 380.2000 75
## 69 D L Vettori 129.0000 129.0000 228
## 70 D M Bravo 270.7500 270.7500 142
## 71 D O Obuya 210.6667 210.6667 181
## 72 D P M Jayawardene 526.4286 526.4286 25
## 73 D R Flynn 124.0000 124.0000 231
## 74 D R Smith 315.5714 315.5714 108
## 75 D R Tuffey 50.0000 50.0000 256
## 76 D Ramdin 169.3333 169.3333 207
## 77 D S Smith 322.3333 322.3333 99
## 78 E C Joyce 299.0000 299.0000 114
## 79 E Chigumbura 356.2500 356.2500 86
## 80 E J G Morgan 679.8571 679.8571 2
## 81 E S Szwarczynski 251.4000 251.4000 154
## 82 F du Plessis 665.7500 665.7500 4
## 83 Farhad Reza 33.0000 33.0000 264
## 84 Fawad Alam 127.5000 127.5000 230
## 85 G B Hogg 147.0000 147.0000 222
## 86 G C Smith 649.0000 649.0000 8
## 87 G C Wilson 281.5714 281.5714 133
## 88 G E F Barnett 163.0000 163.0000 211
## 89 G Gambhir 641.4000 641.4000 9
## 90 G J Bailey 386.0000 386.0000 71
## 91 G J Maxwell 470.0000 470.0000 35
## 92 G Malla 215.0000 215.0000 180
## 93 Gulbadin Naib 276.7500 276.7500 138
## 94 H D R Thirimanne 285.0000 285.0000 128
## 95 H D Rutherford 385.0000 385.0000 72
## 96 H Davids 468.0000 468.0000 36
## 97 H H Gibbs 319.6667 319.6667 104
## 98 H M Amla 528.0000 528.0000 24
## 99 H Masakadza 521.5000 521.5000 29
## 100 H Patel 188.3333 188.3333 194
## 101 I J L Trott 17.0000 17.0000 271
## 102 I K Pathan 144.6667 144.6667 223
## 103 I R Bell 241.6667 241.6667 161
## 104 Imran Nazir 262.3333 262.3333 148
## 105 J A Morkel 349.0000 349.0000 87
## 106 J Botha 160.0000 160.0000 212
## 107 J C Buttler 439.2500 439.2500 46
## 108 J Charles 407.0000 407.0000 63
## 109 J D P Oram 323.1667 323.1667 96
## 110 J D Ryder 295.1667 295.1667 118
## 111 J E C Franklin 199.3333 199.3333 189
## 112 J E Root 463.6667 463.6667 38
## 113 J F Mooney 153.6667 153.6667 218
## 114 J H Kallis 473.0000 473.0000 33
## 115 J J Roy 425.0000 425.0000 53
## 116 J J van der Wath 124.0000 124.0000 232
## 117 J L Ontong 189.0000 189.0000 193
## 118 J M Anderson 14.0000 14.0000 276
## 119 J M Bairstow 238.0000 238.0000 163
## 120 J M Kemp 103.0000 103.0000 241
## 121 J M Vince 366.0000 366.0000 82
## 122 J Mubarak 279.0000 279.0000 135
## 123 J P Duminy 564.3333 564.3333 19
## 124 J R Hopes 48.0000 48.0000 257
## 125 Junaid Siddique 241.0000 241.0000 162
## 126 K A Pollard 323.0000 323.0000 97
## 127 K C Sangakkara 494.4286 494.4286 31
## 128 K D Mills 123.3333 123.3333 233
## 129 K J Coetzer 416.0000 416.0000 57
## 130 K J O'Brien 227.7500 227.7500 172
## 131 K K D Karthik 94.5000 94.5000 243
## 132 K P Pietersen 674.2857 674.2857 3
## 133 K S Williamson 434.0000 434.0000 50
## 134 Kamran Akmal 406.0000 406.0000 65
## 135 Karim Sadiq 224.0000 224.0000 175
## 136 L D Chandimal 317.0000 317.0000 107
## 137 L E Bosman 295.0000 295.0000 119
## 138 L J Wright 320.3333 320.3333 102
## 139 L M P Simmons 394.2222 394.2222 68
## 140 L P C Silva 110.3333 110.3333 239
## 141 L R Taylor 410.4000 410.4000 61
## 142 L Ronchi 342.0000 342.0000 90
## 143 L Vincent 203.0000 203.0000 185
## 144 M A Leask 184.0000 184.0000 196
## 145 M D K J Perera 577.5000 577.5000 17
## 146 M E K Hussey 357.6667 357.6667 85
## 147 M F Maharoof 20.0000 20.0000 268
## 148 M H Cross 279.0000 279.0000 136
## 149 M H Yardy 132.5000 132.5000 226
## 150 M J Clarke 232.7500 232.7500 168
## 151 M J Guptill 582.0000 582.0000 16
## 152 M J Lumb 287.0000 287.0000 126
## 153 M J Prior 221.6667 221.6667 177
## 154 M J Vijay 168.0000 168.0000 208
## 155 M L Hayden 154.0000 154.0000 217
## 156 M L Udawatte 178.0000 178.0000 200
## 157 M N Samuels 414.9000 414.9000 58
## 158 M N van Wyk 321.7500 321.7500 101
## 159 M N Waller 318.7500 318.7500 106
## 160 M Ntini 24.0000 24.0000 267
## 161 M R Gillespie 19.0000 19.0000 270
## 162 M R Swart 534.7500 534.7500 21
## 163 M S Chapman 384.0000 384.0000 73
## 164 M S Dhoni 439.3333 439.3333 45
## 165 M S Sinclair 14.0000 14.0000 277
## 166 M S Wade 248.3333 248.3333 158
## 167 M V Boucher 207.0000 207.0000 183
## 168 M W Machan 411.7500 411.7500 60
## 169 Mahmudullah 290.0000 290.0000 123
## 170 Mandeep Singh 272.0000 272.0000 139
## 171 Mashrafe Mortaza 174.3333 174.3333 202
## 172 Mirwais Ashraf 135.0000 135.0000 225
## 173 Misbah ul Haq 577.2500 577.2500 18
## 174 Mohammad Ashraful 325.8000 325.8000 94
## 175 Mohammad Hafeez 406.1000 406.1000 64
## 176 Mohammad Nabi 293.3333 293.3333 120
## 177 Mohammad Shahzad 450.4286 450.4286 43
## 178 Mohammad Usman 323.0000 323.0000 98
## 179 Mohammad Yousuf 42.0000 42.0000 262
## 180 Mukhtar Ahmed 434.5000 434.5000 48
## 181 Mushfiqur Rahim 369.5000 369.5000 80
## 182 N J O'Brien 250.2857 250.2857 155
## 183 N L McCullum 187.0000 187.0000 195
## 184 N L T Perera 320.0000 320.0000 103
## 185 N R Kumar 190.0000 190.0000 192
## 186 N S Poonia 171.0000 171.0000 206
## 187 N W Bracken 17.0000 17.0000 272
## 188 Nadif Chowdhury 32.0000 32.0000 266
## 189 Naeem Islam 180.0000 180.0000 198
## 190 Najibullah Zadran 284.6667 284.6667 130
## 191 Nasir Hossain 297.7500 297.7500 116
## 192 Nasir Jamshed 424.0000 424.0000 54
## 193 Naved ul Hasan 102.0000 102.0000 242
## 194 Noor Ali Zadran 311.0000 311.0000 111
## 195 Nowroz Mangal 201.0000 201.0000 186
## 196 O A Shah 396.0000 396.0000 67
## 197 P D Collingwood 467.0000 467.0000 37
## 198 P D McGlashan 13.0000 13.0000 282
## 199 P G Fulton 114.0000 114.0000 237
## 200 P J Ongondo 63.0000 63.0000 253
## 201 P L Mommsen 286.5000 286.5000 127
## 202 P R Stirling 470.2000 470.2000 34
## 203 P Utseya 43.0000 43.0000 261
## 204 P W Borren 268.5000 268.5000 143
## 205 Paras Khadka 232.0000 232.0000 169
## 206 Q de Kock 532.6667 532.6667 23
## 207 R A Jadeja 139.0000 139.0000 224
## 208 R D Berrington 381.8000 381.8000 74
## 209 R E Levi 522.0000 522.0000 28
## 210 R G Sharma 459.2222 459.2222 39
## 211 R Gunasekera 235.0000 235.0000 166
## 212 R J Nicol 307.5000 307.5000 112
## 213 R J Peterson 14.0000 14.0000 278
## 214 R M L Taylor 196.0000 196.0000 190
## 215 R N ten Doeschate 233.0000 233.0000 167
## 216 R R Hendricks 296.0000 296.0000 117
## 217 R R Patel 292.0000 292.0000 121
## 218 R R Rossouw 285.0000 285.0000 129
## 219 R R Sarwan 327.0000 327.0000 93
## 220 R R Watson 236.0000 236.0000 164
## 221 R Rampaul 10.0000 10.0000 284
## 222 R S Bopara 312.6667 312.6667 109
## 223 R S Morton 90.5000 90.5000 244
## 224 R T Ponting 523.5000 523.5000 27
## 225 R V Uthappa 215.8000 215.8000 179
## 226 Rizwan Cheema 346.2000 346.2000 88
## 227 S B Styris 375.7500 375.7500 76
## 228 S C J Broad 14.0000 14.0000 279
## 229 S C Williams 224.2000 224.2000 174
## 230 S Chanderpaul 254.6667 254.6667 151
## 231 S Dhawan 322.0000 322.0000 100
## 232 S E Bond 36.0000 36.0000 263
## 233 S E Marsh 166.7500 166.7500 209
## 234 S I Mahmood 11.0000 11.0000 283
## 235 S J Myburgh 438.2500 438.2500 47
## 236 S K Raina 551.1111 551.1111 20
## 237 S L Malinga 159.0000 159.0000 215
## 238 S M Pollock 90.0000 90.0000 245
## 239 S Matsikenyeri 44.0000 44.0000 260
## 240 S O Tikolo 281.8000 281.8000 132
## 241 S P D Smith 259.5000 259.5000 150
## 242 S P Khakurel 200.0000 200.0000 187
## 243 S R Watson 519.0000 519.0000 30
## 244 S T Jayasuriya 526.2000 526.2000 26
## 245 Sabbir Rahman 432.5000 432.5000 51
## 246 Salman Butt 441.0000 441.0000 44
## 247 Samiullah Shenwari 271.0000 271.0000 141
## 248 Sarfraz Ahmed 262.5000 262.5000 147
## 249 Shafiqullah 176.0000 176.0000 201
## 250 Shahadat Hossain 16.0000 16.0000 275
## 251 Shahid Afridi 423.4000 423.4000 55
## 252 Shahzaib Hasan 150.0000 150.0000 220
## 253 Shaiman Anwar 394.0000 394.0000 69
## 254 Shakib Al Hasan 339.4000 339.4000 91
## 255 Sharad Vesawkar 250.0000 250.0000 157
## 256 Sharjeel Khan 370.6667 370.6667 77
## 257 Shoaib Malik 404.9000 404.9000 66
## 258 Sohaib Maqsood 192.0000 192.0000 191
## 259 Soumya Sarkar 319.0000 319.0000 105
## 260 T G Southee 55.0000 55.0000 255
## 261 T L W Cooper 370.2000 370.2000 78
## 262 T M Dilshan 612.4444 612.4444 12
## 263 T M Odoyo 66.0000 66.0000 252
## 264 T Mishra 181.6667 181.6667 197
## 265 T N de Grooth 229.5000 229.5000 170
## 266 T T Bresnan 17.0000 17.0000 273
## 267 T Taibu 235.6667 235.6667 165
## 268 Tamim Iqbal 327.8889 327.8889 92
## 269 U T Khawaja 458.0000 458.0000 40
## 270 Umar Akmal 605.8571 605.8571 13
## 271 V Kohli 622.5000 622.5000 11
## 272 V S Solanki 89.0000 89.0000 246
## 273 V Sehwag 298.5000 298.5000 115
## 274 V Sibanda 244.2000 244.2000 159
## 275 W Barresi 414.6667 414.6667 59
## 276 W T S Porterfield 367.2500 367.2500 81
## 277 W U Tharanga 130.3333 130.3333 227
## 278 W W Hinds 45.0000 45.0000 258
## 279 X M Marshall 109.0000 109.0000 240
## 280 Y K Pathan 266.3333 266.3333 144
## 281 Yasir Arafat 150.0000 150.0000 221
## 282 Younis Khan 407.3333 407.3333 62
## 283 Yuvraj Singh 623.3333 623.3333 10
## 284 Zeeshan Maqsood 370.0000 370.0000 79
library(plotly)
##
## Attaching package: 'plotly'
## The following object is masked from 'package:ggplot2':
##
## last_plot
## The following object is masked from 'package:stats':
##
## filter
## The following object is masked from 'package:graphics':
##
## layout
p <- plot_ly(dataTwenty20Batting, x = ~Name, y = ~avg.x, type = 'scatter',
mode = 'markers', color = batcluster$cluster,
text = ~paste('Rank: ', rank))
p